AIM： To evaluate the use of web-based technologies to assess the learning curve and reassess reproducibility of a simplified version of a classification for gastric magnification chromoendoscopy （MC）. METHODS： As ...AIM： To evaluate the use of web-based technologies to assess the learning curve and reassess reproducibility of a simplified version of a classification for gastric magnification chromoendoscopy （MC）. METHODS： As part of a multicenter trial, a hybrid approach was taken using a CD-ROM, with 20 films of MC lasting 5 s each and an ＂autorun＂ file triggering a local HTML frameset referenced to a remote questionnaire through an Internet connection. Three endoscopists were asked to prospectively and independently classify 10 of these films randomly selected with at least 3 d apart. The answers were centrally stored and returned to participants together with adequate feedback with the right answer. RESULTS： For classification in 3 groups, both intra- [Cohen＇s kappa （K） = 0.79-1.00 to 0.89-1.00] and inter-observer agreement increased from 1st （moderate） to 6th observation （k = 0.94）. Also, agreement with reference increased in the last observations （0.90, 1.00 and 1.00, for observers A, B and C, respectively）. Validity of 100% was obtained by all observers at their 4th observation. When a 4th （sub）group was considered, inter-observer agreement was almost perfect （K = 0.92） at 6th observation. The relation with reference clearly improved into K （0.93-1.00） and sensitivity （75%-100%） at their 6th observations. CONCLUSION： This MC classification seems to be easily explainable and learnable as shown by excellent intra- and inter-observer agreement, and improved agreement with reference. A web system such as the one used in this study may be useful for endoscopic or other image based diagnostic procedures with respect to definition, education and dissemination.展开更多
For accurate and stable haptic rendering, collision detection for interactive haptic applications has to be done by filling in or covering target objects as tightly as possible with bounding volumes （spheres, axis-al...For accurate and stable haptic rendering, collision detection for interactive haptic applications has to be done by filling in or covering target objects as tightly as possible with bounding volumes （spheres, axis-aligned bounding boxes, oriented bounding boxes, or polytopes）. In this paper, we propose a method for creating bounding spheres with respect to the contact levels of details （CLOD）, which can fit objects while maintaining the balance between high speed and precision of collision detection. Our method is composed mainly of two parts： bounding sphere formation and two-level collision detection. To specify further, bounding sphere formation can be divided into two steps： creating spheres and clustering spheres. Two-level collision detection has two stages as well： fast detection of spheres and precise detection in spheres. First, bounding spheres are created for initial fast probing to detect collisions of spheres. Once a collision is probed, a more precise detection is executed by examining the distance between a haptie pointer and each mesh inside the colliding boundaries. To achieve this refmed level of detection, a special data structure of a bounding volume needs to be defined to include all mesh information in the sphere. After performing a number of experiments to examine the usefulness and performance of our method, we have concluded that our algorithm is fast and precise enough for haptic simulations. The high speed detection is achieved through the clustering of spheres, while detection precision is realized by voxel-based direct collision detection. Our method retains its originality through the CLOD by distance-based clustering.展开更多
基金Sociedade Portuguesa de Endoscopia Digestiva (Research Grant 2002)the European Society for Gastrointestinal Endoscopy
文摘AIM： To evaluate the use of web-based technologies to assess the learning curve and reassess reproducibility of a simplified version of a classification for gastric magnification chromoendoscopy （MC）. METHODS： As part of a multicenter trial, a hybrid approach was taken using a CD-ROM, with 20 films of MC lasting 5 s each and an ＂autorun＂ file triggering a local HTML frameset referenced to a remote questionnaire through an Internet connection. Three endoscopists were asked to prospectively and independently classify 10 of these films randomly selected with at least 3 d apart. The answers were centrally stored and returned to participants together with adequate feedback with the right answer. RESULTS： For classification in 3 groups, both intra- [Cohen＇s kappa （K） = 0.79-1.00 to 0.89-1.00] and inter-observer agreement increased from 1st （moderate） to 6th observation （k = 0.94）. Also, agreement with reference increased in the last observations （0.90, 1.00 and 1.00, for observers A, B and C, respectively）. Validity of 100% was obtained by all observers at their 4th observation. When a 4th （sub）group was considered, inter-observer agreement was almost perfect （K = 0.92） at 6th observation. The relation with reference clearly improved into K （0.93-1.00） and sensitivity （75%-100%） at their 6th observations. CONCLUSION： This MC classification seems to be easily explainable and learnable as shown by excellent intra- and inter-observer agreement, and improved agreement with reference. A web system such as the one used in this study may be useful for endoscopic or other image based diagnostic procedures with respect to definition, education and dissemination.
基金supported by Incheon National University Research,Korea(No.20120238)
文摘For accurate and stable haptic rendering, collision detection for interactive haptic applications has to be done by filling in or covering target objects as tightly as possible with bounding volumes （spheres, axis-aligned bounding boxes, oriented bounding boxes, or polytopes）. In this paper, we propose a method for creating bounding spheres with respect to the contact levels of details （CLOD）, which can fit objects while maintaining the balance between high speed and precision of collision detection. Our method is composed mainly of two parts： bounding sphere formation and two-level collision detection. To specify further, bounding sphere formation can be divided into two steps： creating spheres and clustering spheres. Two-level collision detection has two stages as well： fast detection of spheres and precise detection in spheres. First, bounding spheres are created for initial fast probing to detect collisions of spheres. Once a collision is probed, a more precise detection is executed by examining the distance between a haptie pointer and each mesh inside the colliding boundaries. To achieve this refmed level of detection, a special data structure of a bounding volume needs to be defined to include all mesh information in the sphere. After performing a number of experiments to examine the usefulness and performance of our method, we have concluded that our algorithm is fast and precise enough for haptic simulations. The high speed detection is achieved through the clustering of spheres, while detection precision is realized by voxel-based direct collision detection. Our method retains its originality through the CLOD by distance-based clustering.
